{"id":"https://openalex.org/W7225823505","doi":"https://doi.org/10.21203/rs.3.rs-11197667/v1","title":"Dataset curation and signal heterogeneity shape machine learning classification of innate immune transcriptomic responses","display_name":"Dataset curation and signal heterogeneity shape machine learning classification of innate immune transcriptomic responses","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225823505","doi":"https://doi.org/10.21203/rs.3.rs-11197667/v1"},"language":"en","primary_location":{"id":"doi:10.21203/rs.3.rs-11197667/v1","doi":"https://doi.org/10.21203/rs.3.rs-11197667/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11197667/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.21203/rs.3.rs-11197667/v1","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080034288","display_name":"Marina Mancuso","orcid":"https://orcid.org/0000-0002-7262-802X","observed_orcids":["https://orcid.org/0000-0002-7262-802X"]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Marina Mancuso","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006665685","display_name":"Kaitlyn M. Martinez","orcid":"https://orcid.org/0000-0003-0975-2949","observed_orcids":["https://orcid.org/0000-0003-0975-2949"]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kaitlyn M. Martinez","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5078602908","display_name":"Apoorv Shanker","orcid":"https://orcid.org/0000-0001-9914-9515","observed_orcids":["https://orcid.org/0000-0001-9914-9515"]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Apoorv Shanker","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106186972","display_name":"Sarah Nace","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarah Nace","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028076411","display_name":"Kristen M. Wilding","orcid":"https://orcid.org/0000-0001-8476-8946","observed_orcids":["https://orcid.org/0000-0001-8476-8946"]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kristen Wilding","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101341820","display_name":"Makaela M. Montoya","orcid":"https://orcid.org/0000-0002-7391-428X","observed_orcids":["https://orcid.org/0000-0002-7391-428X"]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Makaela M. Montoya","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011091747","display_name":"Daniel E. Jacobsen","orcid":"https://orcid.org/0000-0003-4102-6947","observed_orcids":["https://orcid.org/0000-0003-4102-6947"]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel E. Jacobsen","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087743116","display_name":"Harshini Mukundan","orcid":"https://orcid.org/0000-0002-0931-0545","observed_orcids":["https://orcid.org/0000-0002-0931-0545"]},"institutions":[{"id":"https://openalex.org/I148283060","display_name":"Lawrence Berkeley National Laboratory","ror":"https://ror.org/02jbv0t02","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I148283060","https://openalex.org/I39565521"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Harshini Mukundan","raw_affiliation_strings":["Lawrence Berkeley National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lawrence Berkeley National Laboratory","institution_ids":["https://openalex.org/I148283060"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018016790","display_name":"Jessica Z. Kubicek-Sutherland","orcid":"https://orcid.org/0000-0001-6215-4871","observed_orcids":["https://orcid.org/0000-0001-6215-4871"]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jessica Z. Kubicek-Sutherland","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070280727","display_name":"Carrie A. Manore","orcid":"https://orcid.org/0000-0003-2534-9316","observed_orcids":["https://orcid.org/0000-0003-2534-9316"]},"institutions":[{"id":"https://openalex.org/I1343871089","display_name":"Los Alamos National Laboratory","ror":"https://ror.org/01e41cf67","country_code":"US","type":"facility","lineage":["https://openalex.org/I1330989302","https://openalex.org/I1343871089","https://openalex.org/I198811213","https://openalex.org/I4210120050"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carrie Manore","raw_affiliation_strings":["Los Alamos National Laboratory"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Los Alamos National Laboratory","institution_ids":["https://openalex.org/I1343871089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5080034288"],"corresponding_institution_ids":["https://openalex.org/I1343871089"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.26249998807907104,"subfield":{"id":"https://openalex.org/subfields/2706","display_name":"Critical Care and Intensive Care Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10218","display_name":"Sepsis Diagnosis and Treatment","score":0.26249998807907104,"subfield":{"id":"https://openalex.org/subfields/2706","display_name":"Critical Care and Intensive Care Medicine"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T10885","display_name":"Gene expression and cancer classification","score":0.14550000429153442,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10371","display_name":"Immune Response and Inflammation","score":0.1251000016927719,"subfield":{"id":"https://openalex.org/subfields/2403","display_name":"Immunology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.9056000113487244},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7534000277519226},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6984000205993652},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.6601999998092651},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.6092000007629395},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4993000030517578},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.45019999146461487},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.44339999556541443},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4300000071525574},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.39899998903274536},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3921000063419342},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.35420000553131104},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3522999882698059},{"id":"https://openalex.org/C2776879701","wikidata":"https://www.wikidata.org/wiki/Q25048660","display_name":"Multiple kernel learning","level":4,"score":0.3319999873638153},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.28360000252723694},{"id":"https://openalex.org/C70153297","wikidata":"https://www.wikidata.org/wiki/Q5591907","display_name":"Gradient boosting","level":3,"score":0.2816999852657318},{"id":"https://openalex.org/C69738355","wikidata":"https://www.wikidata.org/wiki/Q1228929","display_name":"Linear discriminant analysis","level":2,"score":0.2800999879837036},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.27810001373291016},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.27219998836517334},{"id":"https://openalex.org/C41587187","wikidata":"https://www.wikidata.org/wiki/Q1501882","display_name":"Generalized linear model","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C139532973","wikidata":"https://www.wikidata.org/wiki/Q2679259","display_name":"Linear classifier","level":3,"score":0.2612999975681305},{"id":"https://openalex.org/C136449434","wikidata":"https://www.wikidata.org/wiki/Q428253","display_name":"Innate immune system","level":3,"score":0.25940001010894775},{"id":"https://openalex.org/C152662350","wikidata":"https://www.wikidata.org/wiki/Q815297","display_name":"Systems biology","level":2,"score":0.25519999861717224},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.25380000472068787},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2524999976158142},{"id":"https://openalex.org/C124535831","wikidata":"https://www.wikidata.org/wiki/Q4915074","display_name":"Biomarker discovery","level":4,"score":0.2517000138759613}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21203/rs.3.rs-11197667/v1","doi":"https://doi.org/10.21203/rs.3.rs-11197667/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11197667/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.21203/rs.3.rs-11197667/v1","doi":"https://doi.org/10.21203/rs.3.rs-11197667/v1","is_oa":true,"landing_page_url":"https://doi.org/10.21203/rs.3.rs-11197667/v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306525896","display_name":"Research Square","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Research Square","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Abstract":[0],"Purpose:":[1],"Host-response":[2],"profiling":[3],"has":[4],"been":[5],"proposed":[6],"as":[7,51,181],"a":[8,45,52,165,182],"strategy":[9],"to":[10,26,54,77,85,91,172,198],"support":[11],"pathogen":[12,17],"classification,":[13],"particularly":[14],"when":[15],"direct":[16],"detection":[18],"is":[19],"delayed.":[20],"However,":[21],"host-response":[22,49,92,142,187],"classifiers":[23,108,135,196],"are":[24],"sensitive":[25],"methodological":[27],"choices,":[28],"including":[29],"classifier":[30],"selection":[31],"and":[32,59,68,103,111,115,126,170,189,203],"variation":[33],"in":[34,47,160],"immune":[35],"signal":[36,60,88],"strength":[37],"across":[38],"sampling":[39],"conditions.":[40],"Methods:":[41],"This":[42],"study":[43],"uses":[44],"controlled":[46],"vitro":[48],"system":[50],"testbed":[53],"evaluate":[55],"how":[56],"dataset":[57,179],"curation":[58],"heterogeneity":[61,158],"influence":[62],"machine":[63],"learning":[64],"classification":[65,188],"performance,":[66],"interpretability,":[67],"generalizability.":[69],"We":[70,94,144],"generated":[71],"transcriptomic":[72,141],"data":[73],"from":[74],"cells":[75],"exposed":[76],"two":[78],"Gram-positive-associated":[79],"agonists":[80],"with":[81],"distinct":[82],"response":[83],"magnitudes":[84],"represent":[86],"within-class":[87,173],"diversity":[89],"relevant":[90,197],"classification.":[93],"compared":[95],"single-layer":[96],"neural":[97],"network":[98],"(NN),":[99],"random":[100],"forest":[101],"(RF),":[102],"generalized":[104],"linear":[105],"model":[106],"(GLM)":[107],"using":[109,118],"overall":[110],"class-based":[112,119],"accuracy":[113],"metrics,":[114],"evaluated":[116],"interpretability":[117,169],"variable":[120],"importance.":[121],"Results:":[122],"Across":[123],"datasets,":[124],"GLM":[125],"RF":[127],"models":[128],"outperformed":[129],"NN":[130],"models,":[131],"indicating":[132],"that":[133,147],"simpler":[134],"may":[136],"be":[137],"preferable":[138],"for":[139,186,192],"small":[140],"datasets.":[143],"further":[145],"found":[146],"feature":[148],"importance":[149],"profiles":[150],"depended":[151],"strongly":[152],"on":[153],"the":[154,161],"degree":[155],"of":[156],"biological":[157],"represented":[159],"training":[162],"data,":[163],"highlighting":[164],"tradeoff":[166],"between":[167],"signal-regime-specific":[168],"robustness":[171],"variation.":[174],"Conclusion:":[175],"These":[176],"findings":[177],"position":[178],"composition":[180],"central":[183],"design":[184],"consideration":[185],"have":[190],"implications":[191],"developing":[193],"more":[194],"robust":[195],"future":[199],"infectious":[200],"disease":[201],"diagnostics":[202],"antimicrobial":[204],"stewardship.":[205]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}
